@inproceedings{lv-etal-2024-urg,
title = "{URG}: A Unified Ranking and Generation Method for Ensembling Language Models",
author = "Lv, Bo and
Tang, Chen and
Zhang, Yanan and
Liu, Xin and
Luo, Ping and
Yu, Yue",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.261",
pages = "4421--4434",
abstract = "Prior research endeavors of the ensemble Large Language Models (LLMs) achieved great success by employing an individual language model (LM) rank before the text generation. However, the use of an individual LM ranker faces two primary challenges: (1) The time-intensive nature of the ranking process, stemming from the comparisons between models; (2) The issue of error propagation arising from the separate ranking and generation models within the framework. In order to overcome these challenges, we propose a novel ensemble framework, namely Unified Ranking and Generation (URG). URG represents an end-to-end framework that jointly ranks the outputs of LLMs and generates fine-grained fusion results, via utilizing a dedicated cross-attention-based module and noise mitigation training against irrelevant information stemming from bad ranking results. Through extensive experimentation and evaluation, we demonstrate the efficiency and effectiveness of our framework in both the ranking and generation tasks. With the close coordination of the ranking and generation modules, our end-to-end framework achieves the state-of-the-art (SOTA) performance on these tasks, and exhibits substantial enhancements to any of the ensembled models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lv-etal-2024-urg">
<titleInfo>
<title>URG: A Unified Ranking and Generation Method for Ensembling Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Lv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ping</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Prior research endeavors of the ensemble Large Language Models (LLMs) achieved great success by employing an individual language model (LM) rank before the text generation. However, the use of an individual LM ranker faces two primary challenges: (1) The time-intensive nature of the ranking process, stemming from the comparisons between models; (2) The issue of error propagation arising from the separate ranking and generation models within the framework. In order to overcome these challenges, we propose a novel ensemble framework, namely Unified Ranking and Generation (URG). URG represents an end-to-end framework that jointly ranks the outputs of LLMs and generates fine-grained fusion results, via utilizing a dedicated cross-attention-based module and noise mitigation training against irrelevant information stemming from bad ranking results. Through extensive experimentation and evaluation, we demonstrate the efficiency and effectiveness of our framework in both the ranking and generation tasks. With the close coordination of the ranking and generation modules, our end-to-end framework achieves the state-of-the-art (SOTA) performance on these tasks, and exhibits substantial enhancements to any of the ensembled models.</abstract>
<identifier type="citekey">lv-etal-2024-urg</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.261</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>4421</start>
<end>4434</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T URG: A Unified Ranking and Generation Method for Ensembling Language Models
%A Lv, Bo
%A Tang, Chen
%A Zhang, Yanan
%A Liu, Xin
%A Luo, Ping
%A Yu, Yue
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F lv-etal-2024-urg
%X Prior research endeavors of the ensemble Large Language Models (LLMs) achieved great success by employing an individual language model (LM) rank before the text generation. However, the use of an individual LM ranker faces two primary challenges: (1) The time-intensive nature of the ranking process, stemming from the comparisons between models; (2) The issue of error propagation arising from the separate ranking and generation models within the framework. In order to overcome these challenges, we propose a novel ensemble framework, namely Unified Ranking and Generation (URG). URG represents an end-to-end framework that jointly ranks the outputs of LLMs and generates fine-grained fusion results, via utilizing a dedicated cross-attention-based module and noise mitigation training against irrelevant information stemming from bad ranking results. Through extensive experimentation and evaluation, we demonstrate the efficiency and effectiveness of our framework in both the ranking and generation tasks. With the close coordination of the ranking and generation modules, our end-to-end framework achieves the state-of-the-art (SOTA) performance on these tasks, and exhibits substantial enhancements to any of the ensembled models.
%U https://aclanthology.org/2024.findings-acl.261
%P 4421-4434
Markdown (Informal)
[URG: A Unified Ranking and Generation Method for Ensembling Language Models](https://aclanthology.org/2024.findings-acl.261) (Lv et al., Findings 2024)
ACL